Optimizing Compound Retrieval Systems

• URL: http://arxiv.org/abs/2504.12063v1
• Date: Wed, 16 Apr 2025 13:18:16 GMT
• Title: Optimizing Compound Retrieval Systems
• Authors: Harrie Oosterhuis, Rolf Jagerman, Zhen Qin, Xuanhui Wang,
• Abstract summary: We propose the concept of compound retrieval systems as a broader class of retrieval systems that apply multiple prediction models.<n>We show how our compound approach can combine the classic BM25 retrieval model with state-of-the-art (pairwise) LLM relevance predictions.<n>Our experimental results show optimized compound retrieval systems provide better trade-offs between effectiveness and efficiency than cascading approaches.
• Score: 30.21938278062652
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modern retrieval systems do not rely on a single ranking model to construct their rankings. Instead, they generally take a cascading approach where a sequence of ranking models are applied in multiple re-ranking stages. Thereby, they balance the quality of the top-K ranking with computational costs by limiting the number of documents each model re-ranks. However, the cascading approach is not the only way models can interact to form a retrieval system. We propose the concept of compound retrieval systems as a broader class of retrieval systems that apply multiple prediction models. This encapsulates cascading models but also allows other types of interactions than top-K re-ranking. In particular, we enable interactions with large language models (LLMs) which can provide relative relevance comparisons. We focus on the optimization of compound retrieval system design which uniquely involves learning where to apply the component models and how to aggregate their predictions into a final ranking. This work shows how our compound approach can combine the classic BM25 retrieval model with state-of-the-art (pairwise) LLM relevance predictions, while optimizing a given ranking metric and efficiency target. Our experimental results show optimized compound retrieval systems provide better trade-offs between effectiveness and efficiency than cascading approaches, even when applied in a self-supervised manner. With the introduction of compound retrieval systems, we hope to inspire the information retrieval field to more out-of-the-box thinking on how prediction models can interact to form rankings.

Related papers

• Killing Two Birds with One Stone: Unifying Retrieval and Ranking with a Single Generative Recommendation Model [71.45491434257106]
  Unified Generative Recommendation Framework (UniGRF) is a novel approach that integrates retrieval and ranking into a single generative model. To enhance inter-stage collaboration, UniGRF introduces a ranking-driven enhancer module. UniGRF significantly outperforms existing models on benchmark datasets.
  arXiv  Detail & Related papers  (2025-04-23T06:43:54Z)
• Reinforcing Compositional Retrieval: Retrieving Step-by-Step for Composing Informative Contexts [67.67746334493302]
  Large Language Models (LLMs) have demonstrated remarkable capabilities across numerous tasks, yet they often rely on external context to handle complex tasks.<n>We propose a tri-encoder sequential retriever that models this process as a Markov Decision Process (MDP)<n>We show that our method consistently and significantly outperforms baselines, underscoring the importance of explicitly modeling inter-example dependencies.
  arXiv  Detail & Related papers  (2025-04-15T17:35:56Z)
• Breaking the Lens of the Telescope: Online Relevance Estimation over Large Retrieval Sets [15.549852480638066]
  We propose a novel paradigm for re-ranking called online relevance estimation. Online relevance estimation continuously updates relevance estimates for a query throughout the ranking process. We validate our approach on TREC benchmarks under two scenarios: hybrid retrieval and adaptive retrieval.
  arXiv  Detail & Related papers  (2025-04-12T22:05:50Z)
• A Collaborative Ensemble Framework for CTR Prediction [73.59868761656317]
  We propose a novel framework, Collaborative Ensemble Training Network (CETNet), to leverage multiple distinct models. Unlike naive model scaling, our approach emphasizes diversity and collaboration through collaborative learning. We validate our framework on three public datasets and a large-scale industrial dataset from Meta.
  arXiv  Detail & Related papers  (2024-11-20T20:38:56Z)
• Adaptive Neural Ranking Framework: Toward Maximized Business Goal for Cascade Ranking Systems [33.46891569350896]
  Cascade ranking is widely used for large-scale top-k selection problems in online advertising and recommendation systems. Previous works on learning-to-rank usually focus on letting the model learn the complete order or top-k order. We name this method as Adaptive Neural Ranking Framework (abbreviated as ARF)
  arXiv  Detail & Related papers  (2023-10-16T14:43:02Z)
• Retrieval-Enhanced Contrastive Vision-Text Models [61.783728119255365]
  We propose to equip vision-text models with the ability to refine their embedding with cross-modal retrieved information from a memory at inference time. Remarkably, we show that this can be done with a light-weight, single-layer, fusion transformer on top of a frozen CLIP. Our experiments validate that our retrieval-enhanced contrastive (RECO) training improves CLIP performance substantially on several challenging fine-grained tasks.
  arXiv  Detail & Related papers  (2023-06-12T15:52:02Z)
• Building an Efficient and Effective Retrieval-based Dialogue System via Mutual Learning [27.04857039060308]
  We propose to combine the best of both worlds to build a retrieval system. We employ a fast bi-encoder to replace the traditional feature-based pre-retrieval model. We train the pre-retrieval model and the re-ranking model at the same time via mutual learning.
  arXiv  Detail & Related papers  (2021-10-01T01:32:33Z)
• Modeling Relevance Ranking under the Pre-training and Fine-tuning Paradigm [44.96049217770624]
  We propose a novel ranking framework called Pre-Rank that takes both user's view and system's view into consideration. To model the user's view of relevance, Pre-Rank pre-trains the initial query-document representations based on large-scale user activities data. To model the system's view of relevance, Pre-Rank further fine-tunes the model on expert-labeled relevance data.
  arXiv  Detail & Related papers  (2021-08-12T10:37:12Z)
• Efficient Data-specific Model Search for Collaborative Filtering [56.60519991956558]
  Collaborative filtering (CF) is a fundamental approach for recommender systems. In this paper, motivated by the recent advances in automated machine learning (AutoML), we propose to design a data-specific CF model. Key here is a new framework that unifies state-of-the-art (SOTA) CF methods and splits them into disjoint stages of input encoding, embedding function, interaction and prediction function.
  arXiv  Detail & Related papers  (2021-06-14T14:30:32Z)
• Towards a Better Tradeoff between Effectiveness and Efficiency in Pre-Ranking: A Learnable Feature Selection based Approach [12.468550800027808]
  In real-world search, recommendation, and advertising systems, the multi-stage ranking architecture is commonly adopted. In this paper, a novel pre-ranking approach is proposed which supports complicated models with interaction-focused architecture. It achieves a better tradeoff between effectiveness and efficiency by utilizing the proposed learnable Feature Selection method.
  arXiv  Detail & Related papers  (2021-05-17T09:48:15Z)
• Probabilistic Case-based Reasoning for Open-World Knowledge Graph Completion [59.549664231655726]
  A case-based reasoning (CBR) system solves a new problem by retrieving cases' that are similar to the given problem. In this paper, we demonstrate that such a system is achievable for reasoning in knowledge-bases (KBs) Our approach predicts attributes for an entity by gathering reasoning paths from similar entities in the KB.
  arXiv  Detail & Related papers  (2020-10-07T17:48:12Z)
• NASE: Learning Knowledge Graph Embedding for Link Prediction via Neural Architecture Search [9.634626241415916]
  Link prediction is the task of predicting missing connections between entities in the knowledge graph (KG) Previous work has tried to use Automated Machine Learning (AutoML) to search for the best model for a given dataset. We propose a novel Neural Architecture Search (NAS) framework for the link prediction task.
  arXiv  Detail & Related papers  (2020-08-18T03:34:09Z)
• Document Ranking with a Pretrained Sequence-to-Sequence Model [56.44269917346376]
  We show how a sequence-to-sequence model can be trained to generate relevance labels as "target words" Our approach significantly outperforms an encoder-only model in a data-poor regime.
  arXiv  Detail & Related papers  (2020-03-14T22:29:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.